Differences

This shows you the differences between two versions of the page.

--- nlp:entity_linking [2021/05/30 09:25] – jmflanig
+++ nlp:entity_linking [2025/06/06 23:29] (current) – jmflanig
@@ Line 2: / Line 2: @@
 ===== Overviews =====
-  * [[https://arxiv.org/pdf/2006.00575.pdf|Sevgili et al 2020 - Neural Entity Linking: A Survey of Models Based on Deep Learning]]
+  * Introduction: [[https://jlab.soe.ucsc.edu/nlp-wiki/lib/exe/fetch.php?media=book:eisenstein-nlp-notes.pdf#page=424|Eisenstein p. 406]]
+  * [[https://ieeexplore.ieee.org/document/6823700|Shen et al 2015 - Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions]]
+  * Section 4.2 of [[https://arxiv.org/pdf/1807.02383.pdf|Singh 2018]]
+  * **[[https://arxiv.org/pdf/2006.00575.pdf|Sevgili et al 2020 - Neural Entity Linking: A Survey of Models Based on Deep Learning]]**
 ===== Papers =====
+See [[https://www.aclweb.org/anthology/search/?q=entity+linking|ACL Anthology - Entity linking]]
+  * [[https://aclanthology.org/W12-3016.pdf|Lin et al 2012 - Entity Linking at Web Scale]]
   * [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.297.6050&rep=rep1&type=pdf|Rao et al 2014 - Entity Linking: Finding Extracted Entities in a Knowledge Base]]  Explains why it's good to use a ranking approach to training an entity linking system in section 5.  "One natural approach to learning would be classification, in which each possible y ∈ Y is classified as being either correct or incorrect. However, such an approach enforces strong constraints: we not only require the correct KB entry to be classified positively, but all other answers to be classified negatively. Additionally, we can expect very unbalanced training, in which the vast majority of possible answers are incorrect... Instead, we select a single correct candidate for a query using a supervised machine learning ranker."
   * [[http://blender.cs.illinois.edu/paper/edl2014overview.pdf|Ji et al 2014 - Overview of TAC-KBP2014 Entity Discovery and Linking Tasks]]
+  * [[https://www.aclweb.org/anthology/N15-1119.pdf|Pan et al 2015 - Unsupervised Entity Linking with Abstract Meaning Representation]]
+  * [[https://www.aclweb.org/anthology/P15-2049.pdf|D’Souza & Ng 2015 - Sieve-Based Entity Linking for the Biomedical Domain]]
   * [[https://www.aclweb.org/anthology/P16-1213.pdf|Sil & Florian 2016 - One for All: Towards Language Independent Named Entity Linking]]
+  * [[https://www.aclweb.org/anthology/D17-1284.pdf|Gupta et al 2017 - Entity Linking via Joint Encoding of Types, Descriptions, and Context]]
+  * [[https://www.aclweb.org/anthology/D17-1007.pdf|Tan et al 2017 - Entity Linking for Queries by Searching Wikipedia Sentences]]
+  * [[https://www.aclweb.org/anthology/N18-1167.pdf|Radhakrishnan et al 2018 - ELDEN: Improved Entity Linking Using Densified Knowledge Graphs]]
+  * [[https://www.aclweb.org/anthology/K18-1050.pdf|Kolitsas & Ganea 2018 - End-to-End Neural Entity Linking]]
+  * [[https://www.aclweb.org/anthology/D18-1126.pdf|Mueller & Durrett 2018 - Effective Use of Context in Noisy Entity Linking]]
+  * [[https://www.aclweb.org/anthology/P19-2026.pdf|Martins et al 2019 - Joint Learning of Named Entity Recognition and Entity Linking]]
+  * [[https://www.aclweb.org/anthology/P19-1335.pdf|Logeswaran et al 2019 - Zero-Shot Entity Linking by Reading Entity Descriptions]]
+  * [[https://www.aclweb.org/anthology/2020.emnlp-main.630.pdf|Botha et al 2020 - Entity Linking in 100 Languages]]
+  * [[https://arxiv.org/pdf/2101.09969.pdf|Ravi et al 2021 - CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata]]
+==== Joint NER + EL ====
+  * [[https://aclanthology.org/P19-2026.pdf|Martins et al 2019 - Joint Learning of Named Entity Recognition and Entity Linking]]
+==== Evaluation ====
+  * [[https://www.aclweb.org/anthology/D19-1066.pdf|Rosales-Mendez et al 2019 - Fine-Grained Evaluation for Entity Linking]]
+==== EL in Dialog ====
+  * [[https://www.aclweb.org/anthology/2021.naacl-industry.4.pdf|Shang et al 2021 - Entity Resolution in Open-domain Conversations]]
+===== Candidate Entities =====
+Most EL systems use a "name dictionary" or "alias table," which is a list from strings to candidate entities they might refer to.  These are usually created using rule-based heuristics, such as running a string edit distance between entities in the knowledge graph and the train, dev and test set text beforehand (this is too slow for an online system).  The papers in this section describe methods of finding candidate entities (and perhaps also linking them at the same time).
+  * [[https://arxiv.org/pdf/1912.01070.pdf|Bansal et al 2019 - Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision]] "Candidate generation" section talks about using string-edit distance for candidate entities.
+  * [[https://arxiv.org/pdf/1909.10506.pdf|Gillick et al 2019 - Learning Dense Representations for Entity Retrieval]] Uses dense representations to retrieve candidate entities
+===== Datasets =====
+  * [[https://github.com/yotam-happy/NEDforNoisyText|WikilinksNED]] - Paper: [[https://arxiv.org/pdf/1706.09147.pdf|Eshel 2017 - Named Entity Disambiguation for Noisy Text]]
 ===== Tutorials =====
@@ Line 13: / Line 47: @@
 ===== Software =====
+===== People =====
+  * [[https://scholar.google.com/citations?user=z7GCqT4AAAAJ&hl=en|Heng Ji]]
 ===== Related Pages =====
   * [[Information Extraction]]